Related papers: Do Protective Perturbations Really Protect Portrai…

Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such as pixel discretization are particularly attractive in…

The proliferation of diffusion-based deepfake technologies poses significant risks for unauthorized and unethical facial image manipulation. While traditional countermeasures have primarily focused on passive detection methods, this paper…

We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Specifically, we experiment with low-pass filtering, PCA, JPEG…

In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can…

Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images…

Federated Learning (FL) facilitates collaborative model training while preserving data locality; however, the exchange of gradients renders the system vulnerable to Gradient Inversion Attacks (GIAs), allowing adversaries to reconstruct…

Adversarial training is a common strategy for enhancing model robustness against adversarial attacks. However, it is typically tailored to the specific attack types it is trained on, limiting its ability to generalize to unseen threat…

The widespread use of image acquisition technologies, along with advances in facial recognition, has raised serious privacy concerns. Face de-identification usually refers to the process of concealing or replacing personal identifiers,…

Recently, generative adversarial networks (GANs) can generate photo-realistic fake facial images which are perceptually indistinguishable from real face photos, promoting research on fake face detection. Though fake face forensics can…

Adversarial attacks can readily disrupt the image classification system, revealing the vulnerability of DNN-based recognition tasks. While existing adversarial perturbations are primarily applied to uncompressed images or compressed images…

Deep neural networks have become the driving force of modern image recognition systems. However, the vulnerability of neural networks against adversarial attacks poses a serious threat to the people affected by these systems. In this paper,…

In this paper, we introduce an innovative method of safeguarding user privacy against the generative capabilities of Neural Radiance Fields (NeRF) models. Our novel poisoning attack method induces changes to observed views that are…

Adversarial examples contain carefully crafted perturbations that can fool deep neural networks (DNNs) into making wrong predictions. Enhancing the adversarial robustness of DNNs has gained considerable interest in recent years. Although…

Despite their great success, deep neural networks rely on high-dimensional, non-robust representations, making them vulnerable to imperceptible perturbations, even in transfer scenarios. To address this, both training-time defenses (e.g.,…

This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single lightweight framework. We name it PRO-Face S, short for…

Recently, zero-shot methods like InstantID have revolutionized identity-preserving generation. Unlike multi-image finetuning approaches such as DreamBooth, these zero-shot methods leverage powerful facial encoders to extract identity…

Recently, a surge of advanced facial editing techniques have been proposed that leverage the generative power of a pre-trained StyleGAN. To successfully edit an image this way, one must first project (or invert) the image into the…

Deep learning-based face recognition (FR) technology exacerbates privacy concerns in photo sharing. In response, the research community developed a suite of anti-FR methods to block identity extraction by unauthorized FR systems. Benefiting…

In this paper, we propose a novel defensive transformation that enables us to maintain a high classification accuracy under the use of both clean images and adversarial examples for adversarially robust defense. The proposed transformation…

We study the problem of defending deep neural network approaches for image classification from physically realizable attacks. First, we demonstrate that the two most scalable and effective methods for learning robust models, adversarial…